Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word "happy" or related forms and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.16
    Boss
    -0.15
    Äįil
    -0.14
    ead
    -0.14
    ät
    -0.14
    .scalablytyped
    -0.14
    ichel
    -0.14
    ease
    -0.14
    uria
    -0.14
    ansson
    -0.14
    POSITIVE LOGITS
    ily
    0.30
    iness
    0.20
    INESS
    0.20
    iest
    0.20
    ening
    0.19
    stance
    0.17
    happy
    0.17
     Happ
    0.17
    illy
    0.17
    yme
    0.17
    Act Density 0.008%

    No Known Activations